AutoJudge: Judge Decoding Without Manual Annotation

• URL: http://arxiv.org/abs/2504.20039v2
• Date: Tue, 30 Sep 2025 17:21:23 GMT
• Title: AutoJudge: Judge Decoding Without Manual Annotation
• Authors: Roman Garipov, Fedor Velikonivtsev, Ivan Ermakov, Ruslan Svirschevski, Vage Egiazarian, Max Ryabinin,
• Abstract summary: AutoJudge is a method that accelerates large language model (LLM) inference with task-specific lossy speculative decoding.<n>Our approach relies on a semi-greedy search algorithm to test which of the mismatches between target and draft models should be corrected.
• Score: 13.451750613294054
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We introduce AutoJudge, a method that accelerates large language model (LLM) inference with task-specific lossy speculative decoding. Instead of matching the original model output distribution token-by-token, we identify which of the generated tokens affect the downstream quality of the response, relaxing the distribution match guarantee so that the "unimportant" tokens can be generated faster. Our approach relies on a semi-greedy search algorithm to test which of the mismatches between target and draft models should be corrected to preserve quality and which ones may be skipped. We then train a lightweight classifier based on existing LLM embeddings to predict, at inference time, which mismatching tokens can be safely accepted without compromising the final answer quality. We evaluate the effectiveness of AutoJudge with multiple draft/target model pairs on mathematical reasoning and programming benchmarks, achieving significant speedups at the cost of a minor accuracy reduction. Notably, on GSM8k with the Llama 3.1 70B target model, our approach achieves up to $\approx2\times$ speedup over speculative decoding at the cost of $\le 1\%$ drop in accuracy. When applied to the LiveCodeBench benchmark, AutoJudge automatically detects programming-specific important tokens, accepting $\ge 25$ tokens per speculation cycle at $2\%$ drop in Pass@1. Our approach requires no human annotation and is easy to integrate with modern LLM inference frameworks.

Related papers

• Multi-Token Prediction via Self-Distillation [73.81494481537636]
  We consider a new approach for converting a pretrained autoregressive language model from a slow single next token prediction model into a fast standalone multi-token prediction model.<n>On GSM8K, our method produces models that can decode more than $3times$ faster on average at $5%$ drop in accuracy relative to single token decoding performance.
  arXiv  Detail & Related papers  (2026-02-05T18:54:48Z)
• Reject Only Critical Tokens: Pivot-Aware Speculative Decoding [31.22793593647334]
  Speculative Decoding (SD) ensures that the output matches the target model's distribution exactly.<n>We propose Pivot-Aware Speculative Decoding, which rejects only those tokens that would lead to a utility drop in the final output.<n>We evaluate our method across various datasets, demonstrating that we can achieve up to $2.5times$ speedup with comparable utility.
  arXiv  Detail & Related papers  (2025-11-01T01:35:10Z)
• LaSeR: Reinforcement Learning with Last-Token Self-Rewarding [54.72617309922891]
  Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a core paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs)<n>Previous practice requires the LLM to sequentially generate solutions and self-verifications using two separate prompt templates, which significantly reduces efficiency.<n>We propose LaSeR (Reinforcement Learning with Last-Token Self-Rewarding), an algorithm that simply augments the original RLVR loss with a MSE loss.
  arXiv  Detail & Related papers  (2025-10-16T17:55:11Z)
• HiSpec: Hierarchical Speculative Decoding for LLMs [15.347747465564458]
  We propose a framework for speculative decoding that exploits $textitearly-exit (EE) models for low-overhead intermediate verification.<n>We show that HiSpec improves throughput by 1.28$times$ on average and by up to 2.01$times$ compared to the baseline single-layer speculation.
  arXiv  Detail & Related papers  (2025-10-01T18:04:14Z)
• SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification [28.63435151584449]
  We propose SelfJudge, which trains judge verifiers via self-supervision of the target model.<n>Our method measures semantic preservation by assessing whether token-substituted responses preserve the meaning of original responses.
  arXiv  Detail & Related papers  (2025-09-26T02:21:12Z)
• Pipeline Parallelism is All You Need for Optimized Early-Exit Based Self-Speculative Decoding [73.67253077506672]
  Large language models (LLMs) deliver impressive generation quality, but incur very high inference cost.<n>Early-exit based self-speculative decoding (EESD) has emerged to mitigate this cost.<n>We propose Pipeline-Parallel Self-Speculative Decoding (PPSD) that fully pipelines the draft and verification work.
  arXiv  Detail & Related papers  (2025-09-19T04:51:41Z)
• R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning [80.104336426172]
  Chain-of-thought (CoT) enhances problem-solving ability of large language models.<n>CoT incurs substantial inference cost due to long autoregressive trajectories.<n>We introduce R-Stitch, a training-free hybrid decoding framework.
  arXiv  Detail & Related papers  (2025-07-23T08:14:36Z)
• Multipole Attention for Efficient Long Context Reasoning [64.94673641704289]
  Large Reasoning Models (LRMs) have shown promising accuracy improvements on complex problem-solving tasks.<n>LRMs need to generate long chain-of-thought reasoning in order to think before answering.<n>We introduce Multipole Attention, which accelerates autoregressive reasoning by only computing exact attention for the most important tokens.
  arXiv  Detail & Related papers  (2025-06-16T03:00:40Z)
• Towards Better Code Generation: Adaptive Decoding with Uncertainty Guidance [28.99265405319943]
  We introduce AdaDec, an adaptive decoding framework guided by token-level uncertainty quantified via Shannon entropy.<n>AdaDec achieves up to a 15.5% improvement in Pass@1 accuracy compared to greedy decoding, matches or outperforms traditional beam search.
  arXiv  Detail & Related papers  (2025-06-10T16:49:46Z)
• Think Before You Accept: Semantic Reflective Verification for Faster Speculative Decoding [48.52389201779425]
  Speculative decoding accelerates inference by generating multiple draft tokens using a lightweight model and verifying them in parallel.<n>Existing verification methods rely heavily on distributional consistency while overlooking semantic correctness.<n>We propose Reflective Verification, a training-free and semantics-aware approach that achieves a better trade-off between correctness and efficiency.
  arXiv  Detail & Related papers  (2025-05-24T10:26:27Z)
• DEL: Context-Aware Dynamic Exit Layer for Efficient Self-Speculative Decoding [7.204881999658682]
  We introduce DEL, a plug-and-play method that adaptively selects the exit layer and speculation length during inference.<n>Del achieves overall speedups of $2.16times$$sim$$2.62times$ over vanilla auto-regressive decoding.
  arXiv  Detail & Related papers  (2025-04-08T01:12:59Z)
• Robust Conformal Prediction with a Single Binary Certificate [58.450154976190795]
  Conformal prediction (CP) converts any model's output to prediction sets with a guarantee to cover the true label with (adjustable) high probability. We propose a robust conformal prediction that produces smaller sets even with significantly lower MC samples.
  arXiv  Detail & Related papers  (2025-03-07T08:41:53Z)
• GRIFFIN: Effective Token Alignment for Faster Speculative Decoding [52.905060461479856]
  GRIFFIN is a framework that incorporates a token-alignable training strategy and a token-alignable draft model. Experiments on LLaMA-series and Vicuna models demonstrate that GRIFFIN achieves an average acceptance length improvement of over 7% and a speedup ratio exceeding 8%.
  arXiv  Detail & Related papers  (2025-02-16T07:06:00Z)
• Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment [25.988070517700848]
  Speculative decoding has been proposed as a technique to accelerate autoregressive generation. We show that even powerful draft models such as GPT-4o, as well as human text cannot achieve high acceptance rates. We ask the following question: Can we adapt verification to recognize correct, but non-aligned replies?
  arXiv  Detail & Related papers  (2025-01-31T17:09:53Z)
• Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation [43.09801987385207]
  Contrastive Language-Image Pretraining (CLIP) excels at learning generalizable image representations but often falls short in zero-shot inference on certain datasets.<n>Test-time adaptation (TTA) mitigates this issue by adjusting components like normalization layers or context prompts, yet it typically requires large batch sizes and extensive augmentations.<n>We propose Token Condensation as Adaptation (TCA), a training-free adaptation method that takes a step beyond standard TC.
  arXiv  Detail & Related papers  (2024-10-16T07:13:35Z)
• Exact Byte-Level Probabilities from Tokenized Language Models for FIM-Tasks and Model Ensembles [23.134664392314264]
  Tokenization is associated with many poorly understood shortcomings in language models (LMs) This work studies how tokenization impacts model performance by analyzing and comparing models with their byte-level counterparts. We introduce the Byte-Token Representation Lemma, a framework that establishes a mapping between the learned token distribution and its equivalent byte-level distribution.
  arXiv  Detail & Related papers  (2024-10-11T23:30:42Z)
• SDSAT: Accelerating LLM Inference through Speculative Decoding with Semantic Adaptive Tokens [4.5888031410244885]
  We propose an acceleration scheme for large language models (LLMs) through Speculative Decoding with Semantic Adaptive Tokens (SDSAT) The primary objective of this design is to enhance the LLM model's ability to generate draft tokens more accurately without compromising its accuracy. Experiments conducted on the CodeLlama-13B and 7B models have yielded speed increases of over 3.5X and 3.0X, respectively.
  arXiv  Detail & Related papers  (2024-03-27T14:54:27Z)
• Block Verification Accelerates Speculative Decoding [23.764655044837113]
  Speculative decoding uses a fast model to draft a block of tokens which are verified in parallel by the target model.<n>In prior works, draft verification is performed independently token-by-token.<n>We propose Block Verification, a simple draft verification algorithm that verifies the entire block jointly.
  arXiv  Detail & Related papers  (2024-03-15T16:28:22Z)
• Object Recognition as Next Token Prediction [99.40793702627396]
  We present an approach to pose object recognition as next token prediction. The idea is to apply a language decoder that auto-regressively predicts the text tokens from image embeddings to form labels.
  arXiv  Detail & Related papers  (2023-12-04T18:58:40Z)
• Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information [67.78183175605761]
  Large Language Models are susceptible to adversarial prompt attacks. This vulnerability underscores a significant concern regarding the robustness and reliability of LLMs. We introduce a novel approach to detecting adversarial prompts at a token level.
  arXiv  Detail & Related papers  (2023-11-20T03:17:21Z)
• SpecTr: Fast Speculative Decoding via Optimal Transport [30.18181671899423]
  We develop a new autoregressive sampling algorithm called $textitSpecTr$, which provides speedup in decoding while ensuring that there is no quality degradation in the decoded output. We experimentally demonstrate that for state-of-the-art large language models, the proposed approach achieves a wall clock speedup of 2.13X, a further 1.37X speedup over speculative decoding on standard benchmarks.
  arXiv  Detail & Related papers  (2023-10-23T17:47:34Z)
• Alternative Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition [49.42732949233184]
  When labeled data is insufficient, semi-supervised learning with the pseudo-labeling technique can significantly improve the performance of automatic speech recognition. Taking noisy labels as ground-truth in the loss function results in suboptimal performance. We propose a novel framework named alternative pseudo-labeling to tackle the issue of noisy pseudo-labels.
  arXiv  Detail & Related papers  (2023-08-12T12:13:52Z)
• WR-ONE2SET: Towards Well-Calibrated Keyphrase Generation [57.11538133231843]
  Keyphrase generation aims to automatically generate short phrases summarizing an input document. The recently emerged ONE2SET paradigm generates keyphrases as a set and has achieved competitive performance. We propose WR-ONE2SET which extends ONE2SET with an adaptive instance-level cost Weighting strategy and a target Re-assignment mechanism.
  arXiv  Detail & Related papers  (2022-11-13T09:56:24Z)
• Certified Robustness to Label-Flipping Attacks via Randomized Smoothing [105.91827623768724]
  Machine learning algorithms are susceptible to data poisoning attacks. We present a unifying view of randomized smoothing over arbitrary functions. We propose a new strategy for building classifiers that are pointwise-certifiably robust to general data poisoning attacks.
  arXiv  Detail & Related papers  (2020-02-07T21:28:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.